© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 75246
    Prev
    Next
    INDEX
    Explanations

    parameters and values related to variables and constraints in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /vue
    -0.07
    aille
    -0.07
    idor
    -0.07
    asser
    -0.06
     Schwartz
    -0.06
    241
    -0.06
    yc
    -0.06
     Kear
    -0.06
    361
    -0.06
    alink
    -0.06
    POSITIVE LOGITS
    çon
    0.06
    è¾
    0.06
    REQUIRED
    0.06
     mÃł
    0.06
    ová
    0.06
    olley
    0.06
    lein
    0.06
    åĵ¥
    0.06
    ennes
    0.06
    acia
    0.06
    Activations Density 0.039%

    No Known Activations